Cluster kernels for semisupervised classification of VHR urban images

In this paper, we present and apply a semisupervised support vector machine based on cluster kernels for the problem of very high resolution image classification. In the proposed setting, a base kernel working with labeled samples only is deformed by a likelihood kernel encoding similarities between unlabeled examples. The resulting kernel is used to train a standard support vector machine (SVM) classifier. Experiments carried out on very high resolution (VHR) multispectral and hyperspectral images using very few labeled examples show the relevancy of the method in the context of urban image classification. Its simplicity and the small number of parameters involved make it versatile and workable by unexperimented users.

A Homogeneous Set-Theoretical Frame for Clustering Fuzzy Relational Data

Our purpose is to provide a set-theoretical frame to clustering fuzzy relational data basically based on cardinality of the fuzzy subsets that represent objects and their complementaries, without applying any crisp property. From this perspective we define a family of fuzzy similarity indexes which includes a set of fuzzy indexes introduced by Tolias et al, and we analyze under which conditions it is defined a fuzzy proximity relation. Following an original idea due to S. Miyamoto we evaluate the similarity between objects and features by means the same mathematical procedure. Joining these concepts and methods we establish an algorithm to clustering fuzzy relational data. Finally, we present an example to make clear all the process

Hereditary completeness for systems of exponentials and reproducing kernels

Vegeu el resum a l'inici del document del fitxer adjunt.

Fronts from two-dimensional dispersal kernels: Beyond the nonoverlapping-generations model

Most integrodifference models of biological invasions are based on the nonoverlapping-generations approximation. However, the effect of multiple reproduction events overlapping generations on the front speed can be very important especially for species with a long life spam . Only in one-dimensional space has this approximation been relaxed previously, although almost all biological invasions take place in two dimensions. Here we present a model that takes into account the overlapping generations effect or, more generally, the stage structure of the population , and we analyze the main differences with the corresponding nonoverlappinggenerations results

Fronts from complex two-dimensional dispersal kernels: theory and application to Reid's paradox

Bimodal dispersal probability distributions with characteristic distances differing by several orders of magnitude have been derived and favorably compared to observations by Nathan [Nature (London) 418, 409 (2002)]. For such bimodal kernels, we show that two-dimensional molecular dynamics computer simulations are unable to yield accurate front speeds. Analytically, the usual continuous-space random walks (CSRWs) are applied to two dimensions. We also introduce discrete-space random walks and use them to check the CSRW results (because of the inefficiency of the numerical simulations). The physical results reported are shown to predict front speeds high enough to possibly explain Reid's paradox of rapid tree migration. We also show that, for a time-ordered evolution equation, fronts are always slower in two dimensions than in one dimension and that this difference is important both for unimodal and for bimodal kernels

Additive utility with intransitive indifference and without independence: A homogeneous case

In the homogeneous case of one type of goods or objects, we prove theexistence of an additive utility function without assuming transitivityof indifference and independence. The representation reveals a positivefactor smaller than 1 that infuences rational choice beyond the utilityfunction and explains departures from these standard axioms of utilitytheory (factor equals to 1).

Biased representation of homothetic preferences on homogeneous sets

In the homogeneous case of one-dimensional objects, we show that any preference relation that is positive and homothetic can be represented by a quantitative utility function and unique bias. This bias may favor or disfavor the preference for an object. In the first case, preferences are complete but not transitive and an object may be preferred even when its utility is lower. In the second case, preferences are asymmetric and transitive but not negatively transitive and it may not be sufficient for an object to have a greater utility for be preferred. In this manner, the bias reflects the extent to which preferences depart from the maximization of a utility function.

Variability of apparently homogeneous soilscapes in São Paulo state, Brazil: I. spatial analysis

The spatial variability of strongly weathered soils under sugarcane and soybean/wheat rotation was quantitatively assessed on 33 fields in two regions in São Paulo State, Brazil: Araras (15 fields with sugarcane) and Assis (11 fields with sugarcane and seven fields with soybean/wheat rotation). Statistical methods used were: nested analysis of variance (for 11 fields), semivariance analysis and analysis of variance within and between fields. Spatial levels from 50 m to several km were analyzed. Results are discussed with reference to a previously published study carried out in the surroundings of Passo Fundo (RS). Similar variability patterns were found for clay content, organic C content and cation exchange capacity. The fields studied are quite homogeneous with respect to these relatively stable soil characteristics. Spatial variability of other characteristics (resin extractable P, pH, base- and Al-saturation and also soil colour), varies with region and, or land use management. Soil management for sugarcane seems to have induced modifications to greater depths than for soybean/wheat rotation. Surface layers of soils under soybean/wheat present relatively little variation, apparently as a result of very intensive soil management. The major part of within-field variation occurs at short distances (< 50 m) in all study areas. Hence, little extra information would be gained by increasing sampling density from, say, 1/km² to 1/50 m². For many purposes, the soils in the study regions can be mapped with the same observation density, but residual variance will not be the same in all areas. Bulk sampling may help to reveal spatial patterns between 50 and 1.000 m.

Variability of apparently homogeneous soilscapes in São Paulo state, Brazil: II. quality of soil maps

The quality of semi-detailed (scale 1:100.000) soil maps and the utility of a taxonomically based legend were assessed by studying 33 apparently homogeneous fields with strongly weathered soils in two regions in São Paulo State: Araras and Assis. An independent data set of 395 auger sites was used to determine purity of soil mapping units and analysis of variance within and between mapping units and soil classification units. Twenty three soil profiles were studied in detail. The studied soil maps have a high purity for some legend criteria, such as B horizon type (> 90%) and soil texture class (> 80%). The purity for the "trophic character" (eutrophic, dystrophic, allic) was only 55% in Assis. It was 88% in Araras, where many soil units had been mapped as associations. In both regions, the base status of clay-textured soils was generally better than suggested by the maps. Analysis of variance showed that mapping was successful for "durable" soil characteristics such as clay content (> 80% of variance explained) and cation exchange capacity (≥ 50% of variance explained) of 0-20 and 60-80 cm layers. For soil characteristics that are easily modified by management, such as base saturation of the 0-20 cm layer, the maps had explained very little (< 15%) of the total variance in the study areas. Intermediate results were obtained for base saturation of the 60-80 cm layer (56% in Assis; 42% in Araras). Variance explained by taxonomic groupings that formed the basis for the legend of the soil maps was similar to, often even smaller than, variance explained by mapping units. The conclusion is that map boundaries have been very carefully located, but descriptions of mapping units could be improved. In future mappings, this could possibly be done at low cost by (a) bulk sampling to remove short range variation and enhance visualization of spatial patterns at distances > 100 m; (b) taking advantage of correlations between easily measured soil characteristics and chemical soil properties and, (c) unbending the link between legend criteria and a taxonomic system. The maps are well suited to obtain an impression of land suitability for high-input farming. Additional field work and data on former land use/management are necessary for the evaluation of chemical properties of surface horizons.

Semi-supervised remote sensing image classification with cluster kernels

A semisupervised support vector machine is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictions.

Design of homogeneous territorial units : a methodological proposal

One of the main questions to solve when analysing geographically added information consists of the design of territorial units adjusted to the objectives of the study. This is related with the reduction of the effects of the Modificable Areal Unit Problem (MAUP). In this paper an optimisation model to solve regionalisation problems is proposed. This model seeks to reduce disadvantages found in previous works about automated regionalisation tools

A comment on the cost of capital for investments with non-homogeneous components

In this paper, the expression for the cost of capital is derived when net and replacement investments exhibit differences in their effective prices due to a different fiscal treatment. It is shown that, contrary to previous results in the literature, the cost of capital should be constructed under an opportunity cost criterion rather than a historical one. This result has some important economic consequences, since the optimizing firm will take into account not only the effective price for the new investments but also consider the opportunity cost of replacing them.

Design of homogeneous territorial units : a methodological proposal

One of the main questions to solve when analysing geographically added information consists of the design of territorial units adjusted to the objectives of the study. This is related with the reduction of the effects of the Modificable Areal Unit Problem (MAUP). In this paper an optimisation model to solve regionalisation problems is proposed. This model seeks to reduce disadvantages found in previous works about automated regionalisation tools

Stochastic generation of homogeneous isotropic turbulence with well-defined-spectra

A precise and simple computational model to generate well-behaved two-dimensional turbulent flows is presented. The whole approach rests on the use of stochastic differential equations and is general enough to reproduce a variety of energy spectra and spatiotemporal correlation functions. Analytical expressions for both the continuous and the discrete versions, together with simulation algorithms, are derived. Results for two relevant spectra, covering distinct ranges of wave numbers, are given.

Ground-state properties of a dilute homogeneous Bose gas of hard disks in two dimensions

The energy and structure of a dilute hard-disks Bose gas are studied in the framework of a variational many-body approach based on a Jastrow correlated ground-state wave function. The asymptotic behaviors of the radial distribution function and the one-body density matrix are analyzed after solving the Euler equation obtained by a free minimization of the hypernetted chain energy functional. Our results show important deviations from those of the available low density expansions, already at gas parameter values x~0.001 . The condensate fraction in 2D is also computed and found generally lower than the 3D one at the same x.